CN109979546A - Network model analysis platform and construction method based on artificial intelligence number pathology - Google Patents
Network model analysis platform and construction method based on artificial intelligence number pathology Download PDFInfo
- Publication number
- CN109979546A CN109979546A CN201910272483.3A CN201910272483A CN109979546A CN 109979546 A CN109979546 A CN 109979546A CN 201910272483 A CN201910272483 A CN 201910272483A CN 109979546 A CN109979546 A CN 109979546A
- Authority
- CN
- China
- Prior art keywords
- network model
- module
- pathological image
- artificial intelligence
- labeling module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 37
- 230000007170 pathology Effects 0.000 title claims abstract description 35
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 26
- 238000010276 construction Methods 0.000 title claims abstract description 12
- 230000001575 pathological effect Effects 0.000 claims abstract description 72
- 238000002372 labelling Methods 0.000 claims abstract description 44
- 238000012549 training Methods 0.000 claims abstract description 35
- 238000000034 method Methods 0.000 claims abstract description 21
- 210000004027 cell Anatomy 0.000 claims description 21
- 238000012795 verification Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 9
- 206010028980 Neoplasm Diseases 0.000 claims description 8
- 201000011510 cancer Diseases 0.000 claims description 8
- 238000012937 correction Methods 0.000 claims description 8
- 238000001514 detection method Methods 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 6
- 210000004698 lymphocyte Anatomy 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 210000001519 tissue Anatomy 0.000 claims 1
- 238000004519 manufacturing process Methods 0.000 abstract description 6
- 238000012800 visualization Methods 0.000 abstract description 4
- 239000012188 paraffin wax Substances 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 abstract description 2
- 239000003814 drug Substances 0.000 description 16
- 238000011160 research Methods 0.000 description 7
- 238000012360 testing method Methods 0.000 description 7
- 238000010171 animal model Methods 0.000 description 6
- 229940079593 drug Drugs 0.000 description 6
- 230000008685 targeting Effects 0.000 description 6
- 238000012827 research and development Methods 0.000 description 5
- 238000003745 diagnosis Methods 0.000 description 4
- 238000010827 pathological analysis Methods 0.000 description 4
- 238000003908 quality control method Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000003759 clinical diagnosis Methods 0.000 description 3
- 238000004445 quantitative analysis Methods 0.000 description 3
- 238000010186 staining Methods 0.000 description 3
- 206010003694 Atrophy Diseases 0.000 description 2
- 206010028851 Necrosis Diseases 0.000 description 2
- 230000037444 atrophy Effects 0.000 description 2
- 230000000740 bleeding effect Effects 0.000 description 2
- 238000005520 cutting process Methods 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000003902 lesion Effects 0.000 description 2
- 230000017074 necrotic cell death Effects 0.000 description 2
- 239000002547 new drug Substances 0.000 description 2
- 230000001737 promoting effect Effects 0.000 description 2
- 230000003245 working effect Effects 0.000 description 2
- 208000004434 Calcinosis Diseases 0.000 description 1
- OYPRJOBELJOOCE-UHFFFAOYSA-N Calcium Chemical compound [Ca] OYPRJOBELJOOCE-UHFFFAOYSA-N 0.000 description 1
- 208000032843 Hemorrhage Diseases 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 208000034158 bleeding Diseases 0.000 description 1
- 230000002308 calcification Effects 0.000 description 1
- 229910052791 calcium Inorganic materials 0.000 description 1
- 239000011575 calcium Substances 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000003255 drug test Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000003118 histopathologic effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 150000002894 organic compounds Chemical class 0.000 description 1
- 230000003285 pharmacodynamic effect Effects 0.000 description 1
- 238000005498 polishing Methods 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/40—ICT specially adapted for the handling or processing of medical references relating to drugs, e.g. their side effects or intended usage
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/60—ICT specially adapted for the handling or processing of medical references relating to pathologies
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Toxicology (AREA)
- Pharmacology & Pharmacy (AREA)
- Medicinal Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention discloses a kind of network model analysis platform and construction method based on artificial intelligence number pathology, mainly solve existing door paraffin section technology or frozen section technique production pathological section existing in the prior art, low efficiency, subjectivity is strong, and the problem that accuracy rate is lower.A kind of network model analysis platform based on artificial intelligence number pathology includes center management server system, the scanning device for pathological section input, editor labeling module, training module, pre- labeling module；The output end of scanning device and the input terminal of editor's labeling module are electrically connected, and the input terminal of the output end and training module of editing labeling module is electrically connected；Training module is trained to form network model to digital pathological image network model after mark；For being electrically connected to the pre- labeling module that the digital pathological image not marked is labeled with network model according to network model.Through the above scheme, the present invention achievees the purpose that quick visualization analyzes pathological section.
Description
Technical field
The present invention relates to medical diagnosis technical fields, specifically, being to be related to the network based on artificial intelligence number pathology
Model analysis platform and construction method.
Background technique
In recent years, as modern medical service crisis, environmental crisis, difficult and complicated cases are attacked in succession, people are urgently wished to not
The disconnected new drug for developing treatment disease is to solve the matter of great urgency.In traditional new drug research and the mode of exploitation, noval chemical compound is set
Meter and synthesis or existing organic compound must first be in laboratory just may be used after inside and outside animal model carries out primary dcreening operation
It can be carried out further pharmacodynamics test and further pharmacology test, finally carry out clinical test.Therefore it is researched and developed in modern medicine
In, zoopery is widely used and puts into.But since medicament research and development is very difficult and expensive, need facing for enormous amount
Bed test support, and a large amount of reality is lowly caused for the observation efficiency of the reaction of experimental animal pathology and drug test result at present
Testing animal model cannot adequately utilize, therefore considerably increase research and development cost.In this regard, we have proposed answer digital pathology
For the observation method of experimental animal pathology result, and then improve the efficiency and accuracy of pathological diagnosis and pathology test.
The pharmaceutical factory of production targeting medicine needs a large amount of standard in the preclinical study of targeting medicine, clinical research and clinical diagnosis
True quantitative analysis improves the research and development cost and clinical test risk of drug, while reducing medicine as a result, workload is very heavy
The market competitiveness of object.
Using prior paraffin microtomy or frozen section technique production pathological section, then now current pathological diagnosis is still
Using manually direct diagosis makes diagnostic result in turn under the microscope；The method low efficiency, subjectivity is strong, and accuracy rate compared with
The low cellular and tissue-pathology changing condition for being unable to fully reflection animal model.
Summary of the invention
The purpose of the present invention is to provide network model analysis platform and construction method based on artificial intelligence number pathology,
With solve existing door paraffin section technology or frozen section technique production pathological section, after by manually directly readding under the microscope
Piece makes diagnostic result method low efficiency in turn, and subjectivity is strong, and the lower cell for being unable to fully reflection animal model of accuracy rate
The problem of histopathologic change situation.
To solve the above-mentioned problems, the invention provides the following technical scheme:
A kind of network model analysis platform based on artificial intelligence number pathology includes center management server system, is used for
Scanning device, the editor labeling module, training module, pre- labeling module of pathological section input；The output end and volume of scanning device
The input terminal for collecting labeling module is electrically connected, and the input terminal of the output end and training module of editing labeling module is electrically connected；Training module pair
Digital pathological image network model is trained to form network model after mark；For according to network model to the number not marked
The pre- labeling module that pathological image is labeled is electrically connected with network model.
Specifically, the signal output end of pre- labeling module comparison input terminal and network model is electrically connected, signal port and instruction
Practice and is connected with correction verification module between module by signal port.
Specifically, the network model analysis platform based on artificial intelligence number pathology further includes center management server system
System, and scanning device are in a wan environment and realize network connection, and the wan environment is to be based on
The domain environment of INTERNET, the center management server system include management server, certificate server, database service
Device, the software to match with the server.
Specifically, the network model analysis platform based on artificial intelligence number pathology further includes for providing pre- mark slice
The quantity of middle various types of cells and the analysis module of situation；Analysis module is electrically connected with pre- labeling module.
Specifically, network model includes sorter network model, target detection network model and semantic segmentation network model；Point
Class network model is used for the tissue typing of pathological image；Target detection network model for HE or IHC image target identification and
Positioning；Semantic segmentation network model organizes for identification, the boundary of cell and profile.
Specifically, scanning device is digital pathology scanner, and digital pathological image is WSI format.
It is a kind of based on artificial intelligence number pathology network model analysis construction method the following steps are included:
(S1) pathological section, the digital pathological image being sliced are scanned using scanning device；
(S2) digital pathological image that step (S1) obtains is uploaded to editor's labeling module, mark personnel mark in editor
The digital pathological image of slice is labeled in module；
(S3) digital pathological image after step (S2) editor mark is sent to training module and carries out to digital pathological image
Training obtains network model；
(S4) digital pathological image for not marking slice is uploaded to pre- labeling module, and pre- labeling module is according to step (S4)
Network model is labeled the digital pathological image for not marking slice.
Specifically, the construction method of the network model analysis platform based on artificial intelligence number pathology further includes optimization network
The method of calibration of model, detailed process is as follows:
(A1) pre- labeling module will carry out the digital pathological image after marking in advance and be sent to correction verification module, algorithm personnel judgement
Whether slice mark is qualified, is that the digital pathological image marked in advance is then sent to network model, no, thens follow the steps (A2)；
(A2) algorithm personnel analysis marks underproof reason in advance, optimizes network model according to reason；It repeats step (A1)
It is qualified to the digital pathological image marked in advance；
Specifically, detailed process is as follows for training module training in step (S3):
(S321) to the slice marked, the common ground of existing markup information is extracted, database is contrasted；
(S322) digital pathological image will not be marked be first divided into several pieces；
(S323) part of these images is compared with step (S321) comparison database one by one, identifies, screens it
Common trait；It is consistent with content existing in comparison database, it is named and is stored to comparison database；It is incongruent
Then without mark.
Specifically, identification, the detailed process of screening in step (S323) are as follows: various cells, which occupy, in comparison sectioning image cuts
The general profile of the main distributed areas of piece and the ratio of various cells and cancer nests；Various cells include cancer cell, lymphocyte,
Hyperblastosis.
Compared with prior art, the invention has the following advantages:
(1) administrative staff using scanning device obtain the digital pathological image of pathology in the present invention, after be uploaded to it is flat
Digital pathological image is marked in platform, mark personnel, and Quality Control personnel carry out quality control to the digital pathological image for completing label
System, it is qualified to be just sent to training module, it is underproof be sent to editor's labeling module allow mark personnel modify to it or
Again it marks, guarantees the accuracy of initial data；It stores after training module training to network model；The network model is for all kinds of
Quick diagnosis is done in the pharmaceutical factory for needing to be sliced quick analyzing and diagnosing, has saved a large amount of manual workings；For example hospital can pass through the net
Network model quickly analyzes the pathological section of patient, largely reduces the workload of medical staff, such as production targeting
The pharmaceutical factory of medicine can obtain accurate quantitative analysis knot in the preclinical study of targeting medicine, clinical research and clinical diagnosis
Fruit reduces the research and development cost of drug and increases the confidence level of drug study, while promoting the market competitiveness of drug；In use,
The slice not marked is uploaded to pre- labeling module, by the comparison of itself and network model, slice is marked in advance；It is quickly quasi-
Really effectively analyze the cell of all kinds of lesions in slice.
(2) it is errorless to carry out verification determination by mark personnel in correction verification module for slice of the present invention after pre- mark
Afterwards, after being sent to the training of training module network model, it is trained study again, it is continuous to optimize abundant network model.
(3) present invention realizes pathological analysis visualization by analysis module, will study region of interest ROI (bleeding, calcium
Change, necrosis, atrophy, cancer nests, specific stain, unspecific staining etc.) it is interested elect, convenient for pathological study personnel it is accurate
Evaluation.
Detailed description of the invention
Fig. 1 is the circuit theory schematic diagram of platform of the present invention.
Fig. 2 is flow chart of the present invention.
Specific embodiment
Present invention will be further explained below with reference to the attached drawings and examples, and embodiments of the present invention include but is not limited to
The following example.
As shown in Figure 1, a kind of network model analysis platform based on artificial intelligence number pathology includes centre management service
Device system, the scanning device for pathological section input, editor labeling module, training module, pre- labeling module；Scanning device
Output end and the input terminal of editor's labeling module are electrically connected, and the input terminal of the output end and training module of editing labeling module is electrically connected；
Training module is trained to form network model to digital pathological image network model after mark；For according to network model to not
The pre- labeling module that the digital pathological image of mark is labeled is electrically connected with network model.
Administrative staff obtain the digital pathological image of pathology using scanning device, after be uploaded to platform, mark personnel
Digital pathological image is marked, Quality Control personnel to complete label digital pathological image carry out quality control, it is qualified just
It is sent to training module at heart, the underproof editor's labeling module that is sent to allows mark personnel to modify to it or mark again
Note, guarantees the accuracy of initial data；It stores after training module training to network model；The network model is cut for all kinds of needs
Quick diagnosis is done in the pharmaceutical factory of piece quick diagnosis, has saved a large amount of manual workings；For example hospital can be by the network model to disease
The pathological section of people is quickly analyzed, and the workload of medical staff, such as the pharmaceutical factory energy of production targeting medicine are largely reduced
It is enough to obtain accurate quantitative analysis in the preclinical study of targeting medicine, clinical research and clinical diagnosis as a result, reducing medicine
The research and development cost of object and the confidence level for increasing drug study, while promoting the market competitiveness of drug；In use, will not mark
Slice is uploaded to pre- labeling module, by the comparison of itself and network model, is marked in advance to slice；Quick and precisely effective point
The cell of all kinds of lesions in slice is precipitated.
As in preferred embodiments of the present invention, the signal output end of pre- labeling module comparison input terminal and network model is electric
Even, correction verification module is connected between signal port and training module signal port；Pre- labeling module can also have other typing numbers
According to mode；Slice after pre- mark, carried out in correction verification module by mark personnel verification determine it is errorless after, be sent to instruction
After practicing module network model training, it is trained study again, it is continuous to optimize abundant network model.
As in preferred embodiments of the present invention, the network model analysis platform based on artificial intelligence number pathology further includes
Center management server system, and scanning device are in a wan environment and realize network connection, the wide area
Net environment is the domain environment based on INTERNET, and the center management server system includes management server, authentication service
Device, database server, the software to match with the server.
As in preferred embodiments of the present invention, the network model analysis platform based on artificial intelligence number pathology further includes
For providing the quantity of various types of cells and the analysis module of situation in pre- mark slice；Analysis module is electrically connected with pre- labeling module；
By analysis module realize pathological analysis visualization, will research region of interest ROI (bleeding, calcification, necrosis, atrophy, cancer nests,
Specific stain, unspecific staining etc.) it is interested elect, be convenient for pathological study personnel accurate evaluation.
Research region of interest ROI accurate quantification is evaluated, such as: quantity, density, area, staining power, ratio, albumen
Intensity and the intensity of gene magnification of expression etc..
Specifically, network model includes sorter network model, target detection network model and semantic segmentation network model；Point
Class network model is used for the tissue typing of pathological image；Target detection network model for HE or IHC image target identification and
Positioning；Semantic segmentation network model organizes for identification, the boundary of cell and profile.
As in preferred embodiments of the present invention, scanning device is digital pathology scanner, and digital pathological image is WSI lattice
Formula；Also the equipment that other forms can be selected, is converted into electronic picture format for pathological section.
As shown in Fig. 2, a kind of construction method of the network model analysis based on artificial intelligence number pathology includes following step
It is rapid:
(S1) pathological section, the digital pathological image being sliced are scanned using scanning device；
(S2) digital pathological image that step (S1) obtains is uploaded to editor's labeling module, mark personnel mark in editor
The digital pathological image of slice is labeled in module；
(S3) digital pathological image after step (S2) editor mark is sent to training module and carries out to digital pathological image
Training obtains network model；
(S5) digital pathological image for not marking slice is uploaded to pre- labeling module, and the pre- labeling module of network model is according to step
Suddenly the network model of (S4) is labeled the digital pathological image for not marking slice.
As in preferred embodiments of the present invention, the building of the network model analysis platform based on artificial intelligence number pathology
Method further includes optimizing the method for calibration of network model, and detailed process is as follows:
(A1) pre- labeling module will carry out the digital pathological image after marking in advance and be sent to correction verification module, algorithm personnel judgement
Whether slice mark is qualified, is that the digital pathological image marked in advance is then sent to network model, no, thens follow the steps (A2)；
(A2) algorithm personnel analysis marks underproof reason in advance, optimizes network model according to reason；It repeats step (A1)
It is qualified to the digital pathological image marked in advance；Underproof reason be algorithm not to, manually the digital pathological picture that marks is too
Make the precision of network model less not enough or sample is not complete；The digital pathological section of professional's mark is equivalent to one for standard
The standard of a comparison is sliced.
As in preferred embodiments of the present invention, detailed process is as follows for training module training in step (S3):
(S321) to the slice marked, the common ground of existing markup information is extracted, database is contrasted；
(S322) digital pathological image will not be marked be first divided into several pieces；
(S323) part of these images is compared with step (S321) comparison database one by one, identifies, screens it
Common trait；It is consistent with content existing in comparison database, it is named and is stored to comparison database；It is incongruent
Then without mark.
It as in preferred embodiments of the present invention, is identified in step (S323), the detailed process of screening are as follows: comparison slice map
Various cells occupy the general profile of the main distributed areas of slice and the ratio of various cells and cancer nests as in；Various cell packets
Include cancer cell, lymphocyte, hyperblastosis.
Through the invention complete digital pathological image it is quick upload, search, inquiry, browsing, delete, restore etc. operate；
Online annotation tool is provided, mark can be created on the digital image or modification is marked and saved at any time, it is right according to label (Tags)
Mark figure is classified and is counted, while can be managed to all labeled data, can search for access, edit-modify etc..
According to the demand of labeled data and research and training, selects cutting method and define Class classification, carry out image labeling
The customized cutting preview of the visualization in region.
According to above-described embodiment, the present invention can be realized well.It is worth noting that before based on said structure design
It puts, to solve same technical problem, even if that makes in the present invention is some without substantive change or polishing, is used
Technical solution essence still as the present invention, therefore it should also be as within the scope of the present invention.
Claims (10)
1. a kind of network model analysis platform based on artificial intelligence number pathology, which is characterized in that including being used for pathological section
Scanning device, the editor labeling module, training module, pre- labeling module of input；The output end and editor's mark mould of scanning device
The input terminal of block is electrically connected, and the input terminal of the output end and training module of editing labeling module is electrically connected；Training module is to number after mark
Word pathological image network model is trained to form network model；For according to network model to the digital pathological image not marked
Pre- labeling module and the network model being labeled are electrically connected.
2. the network model analysis platform according to claim 1 based on artificial intelligence number pathology, which is characterized in that pre-
The signal output end of labeling module comparison input terminal and network model is electrically connected, between signal port and training module signal port
It is connected with correction verification module.
3. the network model analysis platform according to claim 1 based on artificial intelligence number pathology, which is characterized in that also
Network connection is in a wan environment and realized including center management server system, and scanning device, it is described
Wan environment is the domain environment based on INTERNET, and the center management server system includes management server, certification
Server, database server, the software to match with the server.
4. the network model analysis platform according to claim 1-3 based on artificial intelligence number pathology, special
Sign is, further includes for providing the quantity of various types of cells and the analysis module of situation in pre- mark slice；Analysis module and pre-
Labeling module is electrically connected.
5. the network model analysis platform according to claim 1-3 based on artificial intelligence number pathology, special
Sign is that network model includes sorter network model, target detection network model and semantic segmentation network model；Sorter network mould
Type is used for the tissue typing of pathological image；Target detection network model is used for the target identification and positioning of HE or IHC image；It is semantic
Segmentation network model organizes for identification, the boundary of cell and profile.
6. the network model analysis platform according to claim 4 based on artificial intelligence number pathology, which is characterized in that sweep
Retouching equipment is digital pathology scanner, and digital pathological image is WSI format.
7. a kind of construction method of the network model analysis based on artificial intelligence number pathology, which is characterized in that including following step
It is rapid:
(S1) pathological section, the digital pathological image being sliced are scanned using scanning device；
(S2) digital pathological image that step (S1) obtains is uploaded to editor's labeling module, mark personnel are in editor's labeling module
On the digital pathological image of slice is labeled；
(S3) digital pathological image after step (S2) editor mark is sent to training module and is trained to digital pathological image
Obtain network model；
(S4) digital pathological image for not marking slice is uploaded to pre- labeling module, and pre- labeling module is according to the network of step (S3)
Model is labeled the digital pathological image for not marking slice.
8. the construction method of the network model analysis platform according to claim 6 based on artificial intelligence number pathology,
It is characterized in that, further includes the method for calibration for optimizing network model, detailed process is as follows:
(A1) pre- labeling module is sent to correction verification module for the digital pathological image after marking in advance is carried out, and algorithm personnel judge slice
Whether mark is qualified, is that the digital pathological image marked in advance is then sent to network model, no, thens follow the steps (A2)；
(A2) algorithm personnel analysis marks underproof reason in advance, optimizes network model according to reason；Step (A1) is repeated to pre-
The digital pathological image of mark is qualified.
9. the construction method of the network model analysis platform according to claim 7 based on artificial intelligence number pathology,
It is characterized in that,
Detailed process is as follows for training module training in step (S3):
(S321) to the slice marked, the common ground of existing markup information is extracted, database is contrasted；
(S322) digital pathological image will not be marked be first divided into several pieces；
(S323) part of these images is compared with step (S321) comparison database one by one, is identified, it is common to screen it
Feature；It is consistent with content existing in comparison database, it is named and is stored to comparison database；It is incongruent then not
It is labeled.
10. the construction method of the network model analysis platform according to claim 8 based on artificial intelligence number pathology,
It is characterized in that, identification, the detailed process of screening in step (S323) are as follows: various cells occupy the master of slice in comparison sectioning image
Want the ratio of distributed areas and various cells and the general profile of cancer nests；Various cells include cancer cell, lymphocyte, tissue increasing
It is raw.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910272483.3A CN109979546A (en) | 2019-04-04 | 2019-04-04 | Network model analysis platform and construction method based on artificial intelligence number pathology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910272483.3A CN109979546A (en) | 2019-04-04 | 2019-04-04 | Network model analysis platform and construction method based on artificial intelligence number pathology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109979546A true CN109979546A (en) | 2019-07-05 |
Family
ID=67083139
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910272483.3A Pending CN109979546A (en) | 2019-04-04 | 2019-04-04 | Network model analysis platform and construction method based on artificial intelligence number pathology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109979546A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110570931A (en) * | 2019-04-01 | 2019-12-13 | 成都大学 | medical information platform |
| CN111681738A (en) * | 2020-06-09 | 2020-09-18 | 平安科技（深圳）有限公司 | Pathological section scanning and analysis based integrated method, device, equipment and medium |
| CN111860487A (en) * | 2020-07-28 | 2020-10-30 | 天津恒达文博科技股份有限公司 | Inscription marking detection and recognition system based on deep neural network |
| CN111899214A (en) * | 2020-06-12 | 2020-11-06 | 西安交通大学 | Pathological section scanning analysis device and pathological section scanning method |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110075897A1 (en) * | 2009-09-30 | 2011-03-31 | Genera Electric Company | Stain-based optimized compression of digital pathology slides |
| US20140270431A1 (en) * | 2013-03-15 | 2014-09-18 | Sony Corporation | Characterizing pathology images with statistical analysis of local neural network responses |
| CN105975793A (en) * | 2016-05-23 | 2016-09-28 | 麦克奥迪（厦门）医疗诊断系统有限公司 | Auxiliary cancer diagnosis method based on digital pathological images |
| US20160321809A1 (en) * | 2013-10-01 | 2016-11-03 | Ventana Medical Systems, Inc. | Line-based image registration and cross-image annotation devices, systems and methods |
| CN106991355A (en) * | 2015-09-10 | 2017-07-28 | 天津中科智能识别产业技术研究院有限公司 | The face identification method of the analytical type dictionary learning model kept based on topology |
| CN107704878A (en) * | 2017-10-09 | 2018-02-16 | 南京大学 | A kind of high-spectral data storehouse semi-automation method for building up based on deep learning |
| CN108288506A (en) * | 2018-01-23 | 2018-07-17 | 雨声智能科技（上海）有限公司 | A kind of cancer pathology aided diagnosis method based on artificial intelligence technology |
| CN108694718A (en) * | 2018-05-28 | 2018-10-23 | 中山大学附属第六医院 | The same period new chemoradiation therapy curative effect evaluation system and method before rectal cancer |
| CN108764329A (en) * | 2018-05-24 | 2018-11-06 | 复旦大学附属华山医院北院 | A kind of construction method of lung cancer pathology image data set |
| CN108833409A (en) * | 2018-06-15 | 2018-11-16 | 北京网思科平科技有限公司 | webshell detection method and device based on deep learning and semi-supervised learning |
| CN108846828A (en) * | 2018-05-04 | 2018-11-20 | 上海交通大学 | A kind of pathological image target-region locating method and system based on deep learning |
| CN109165623A (en) * | 2018-09-07 | 2019-01-08 | 北京麦飞科技有限公司 | Rice scab detection method and system based on deep learning |
| CN109359697A (en) * | 2018-10-30 | 2019-02-19 | 国网四川省电力公司广元供电公司 | Graph image recognition methods and inspection system used in a kind of power equipment inspection |
| CN109377803A (en) * | 2018-12-06 | 2019-02-22 | 成都大学 | Digitize micro- interaction platform |
| CN109493346A (en) * | 2018-10-31 | 2019-03-19 | 浙江大学 | It is a kind of based on the gastric cancer pathology sectioning image dividing method more lost and device |
-
2019
- 2019-04-04 CN CN201910272483.3A patent/CN109979546A/en active Pending
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110075897A1 (en) * | 2009-09-30 | 2011-03-31 | Genera Electric Company | Stain-based optimized compression of digital pathology slides |
| US20140270431A1 (en) * | 2013-03-15 | 2014-09-18 | Sony Corporation | Characterizing pathology images with statistical analysis of local neural network responses |
| US20160321809A1 (en) * | 2013-10-01 | 2016-11-03 | Ventana Medical Systems, Inc. | Line-based image registration and cross-image annotation devices, systems and methods |
| CN106991355A (en) * | 2015-09-10 | 2017-07-28 | 天津中科智能识别产业技术研究院有限公司 | The face identification method of the analytical type dictionary learning model kept based on topology |
| CN105975793A (en) * | 2016-05-23 | 2016-09-28 | 麦克奥迪（厦门）医疗诊断系统有限公司 | Auxiliary cancer diagnosis method based on digital pathological images |
| CN107704878A (en) * | 2017-10-09 | 2018-02-16 | 南京大学 | A kind of high-spectral data storehouse semi-automation method for building up based on deep learning |
| CN108288506A (en) * | 2018-01-23 | 2018-07-17 | 雨声智能科技（上海）有限公司 | A kind of cancer pathology aided diagnosis method based on artificial intelligence technology |
| CN108846828A (en) * | 2018-05-04 | 2018-11-20 | 上海交通大学 | A kind of pathological image target-region locating method and system based on deep learning |
| CN108764329A (en) * | 2018-05-24 | 2018-11-06 | 复旦大学附属华山医院北院 | A kind of construction method of lung cancer pathology image data set |
| CN108694718A (en) * | 2018-05-28 | 2018-10-23 | 中山大学附属第六医院 | The same period new chemoradiation therapy curative effect evaluation system and method before rectal cancer |
| CN108833409A (en) * | 2018-06-15 | 2018-11-16 | 北京网思科平科技有限公司 | webshell detection method and device based on deep learning and semi-supervised learning |
| CN109165623A (en) * | 2018-09-07 | 2019-01-08 | 北京麦飞科技有限公司 | Rice scab detection method and system based on deep learning |
| CN109359697A (en) * | 2018-10-30 | 2019-02-19 | 国网四川省电力公司广元供电公司 | Graph image recognition methods and inspection system used in a kind of power equipment inspection |
| CN109493346A (en) * | 2018-10-31 | 2019-03-19 | 浙江大学 | It is a kind of based on the gastric cancer pathology sectioning image dividing method more lost and device |
| CN109377803A (en) * | 2018-12-06 | 2019-02-22 | 成都大学 | Digitize micro- interaction platform |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110570931A (en) * | 2019-04-01 | 2019-12-13 | 成都大学 | medical information platform |
| CN111681738A (en) * | 2020-06-09 | 2020-09-18 | 平安科技（深圳）有限公司 | Pathological section scanning and analysis based integrated method, device, equipment and medium |
| CN111681738B (en) * | 2020-06-09 | 2024-05-07 | 平安科技（深圳）有限公司 | Integrated method, device, equipment and medium based on pathological section scanning and analysis |
| CN111899214A (en) * | 2020-06-12 | 2020-11-06 | 西安交通大学 | Pathological section scanning analysis device and pathological section scanning method |
| CN111899214B (en) * | 2020-06-12 | 2022-12-09 | 西安交通大学 | Pathological section scanning analysis device and pathological section scanning method |
| CN111860487A (en) * | 2020-07-28 | 2020-10-30 | 天津恒达文博科技股份有限公司 | Inscription marking detection and recognition system based on deep neural network |
| CN111860487B (en) * | 2020-07-28 | 2022-08-19 | 天津恒达文博科技股份有限公司 | Inscription marking detection and recognition system based on deep neural network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chakraborty et al. | Modified cuckoo search algorithm in microscopic image segmentation of hippocampus | |
| CN109979546A (en) | Network model analysis platform and construction method based on artificial intelligence number pathology | |
| JP6184964B2 (en) | Methods and systems for analyzing biological samples with spectral images. | |
| CA2859269C (en) | System for detecting genes in tissue samples | |
| Barros et al. | PathoSpotter-K: A computational tool for the automatic identification of glomerular lesions in histological images of kidneys | |
| US7027627B2 (en) | Medical decision support system and method | |
| JP2021063819A (en) | Systems and methods for comprehensive multi-assay tissue analysis | |
| Habtemariam et al. | Cervix type and cervical cancer classification system using deep learning techniques | |
| EP4104093A1 (en) | Federated learning system for training machine learning algorithms and maintaining patient privacy | |
| CN112884724B (en) | Intelligent judgment method and system for lung cancer histopathological typing | |
| WO2022036086A1 (en) | Machine learning models for cell localization and classification learned using repel coding | |
| CN113793305A (en) | Pathological image classification and identification method and system integrating multiple information | |
| CN115909006B (en) | Mammary tissue image classification method and system based on convolution transducer | |
| CN110838094B (en) | Pathological section dyeing style conversion method and electronic equipment | |
| Yazdi et al. | A multilayered urban tree dataset of point clouds, quantitative structure and graph models | |
| CN115564750A (en) | Intraoperative frozen slice image identification method, intraoperative frozen slice image identification device, intraoperative frozen slice image identification equipment and intraoperative frozen slice image storage medium | |
| CN115049605A (en) | Artificial intelligence processing and analyzing method for liver disease pathological tissue image | |
| WO2022035609A1 (en) | Active learning system for digital pathology | |
| Totu et al. | An objective scoring framework for histology slide image mosaics applicable for the reliable benchmarking of image quality assessment algorithms | |
| CN110598561A (en) | Cell slide analysis method and device based on machine learning and storage medium | |
| US12014830B2 (en) | System and method for automation of surgical pathology processes using artificial intelligence | |
| Reed et al. | Osteocyte-based image analysis for quantitation of histologically apparent femoral head osteonecrosis: application to an emu model | |
| Vesterinen et al. | Helsinki Biobank's Digital Pathology Solutions in Processing Tissue Samples. | |
| Hossain et al. | UCF Lymp Node Patch Batch | |
| Hossain et al. | UCF Breast Patch |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190705 |
|
| RJ01 | Rejection of invention patent application after publication |